Hugging Face's logo

hpcai-tech
/
Colossal-LLaMA-2-13b-base

Text Generation
Transformers
PyTorch
Chinese
English
llama
text-generation-inference
Model card Files
xet
Community
1
Camille7777 commited on
Commit
ba49590
·
1 Parent(s): e962b2f

upload model weights

Browse files
Files changed (33) hide show
  1. config.json +30 -0
  2. generation_config.json +9 -0
  3. pytorch_model-00001.bin +3 -0
  4. pytorch_model-00002.bin +3 -0
  5. pytorch_model-00003.bin +3 -0
  6. pytorch_model-00004.bin +3 -0
  7. pytorch_model-00005.bin +3 -0
  8. pytorch_model-00006.bin +3 -0
  9. pytorch_model-00007.bin +3 -0
  10. pytorch_model-00008.bin +3 -0
  11. pytorch_model-00009.bin +3 -0
  12. pytorch_model-00010.bin +3 -0
  13. pytorch_model-00011.bin +3 -0
  14. pytorch_model-00012.bin +3 -0
  15. pytorch_model-00013.bin +3 -0
  16. pytorch_model-00014.bin +3 -0
  17. pytorch_model-00015.bin +3 -0
  18. pytorch_model-00016.bin +3 -0
  19. pytorch_model-00017.bin +3 -0
  20. pytorch_model-00018.bin +3 -0
  21. pytorch_model-00019.bin +3 -0
  22. pytorch_model-00020.bin +3 -0
  23. pytorch_model-00021.bin +3 -0
  24. pytorch_model-00022.bin +3 -0
  25. pytorch_model-00023.bin +3 -0
  26. pytorch_model-00024.bin +3 -0
  27. pytorch_model-00025.bin +3 -0
  28. pytorch_model-00026.bin +3 -0
  29. pytorch_model-00027.bin +3 -0
  30. pytorch_model.bin.index.json +370 -0
  31. special_tokens_map.json +23 -0
  32. tokenizer.model +3 -0
  33. tokenizer_config.json +34 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Colossal-LLaMA-2-13b-Base-V3",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "layer_norm_eps": 1e-05,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 1,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.32.0",
27
+ "use_cache": true,
28
+ "use_parallel_residual": false,
29
+ "vocab_size": 69104
30
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "temperature": 0.3,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.31.0"
9
+ }
pytorch_model-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3ed499cc70e37ec0d6de1d66495f3ef7c71dd1df2a93619cda6860e81d6dcfa
3
+ size 1058900343
pytorch_model-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e5a9324749cd39dcd14ddb23f98683d339e028efcae664abb776b8e08eb81d7
3
+ size 1022407812
pytorch_model-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffb6bb985dd403aa01f1bf75645dac898931ea4b584e473d4aaa353af7f70eeb
3
+ size 1022386674
pytorch_model-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693553841b27d74fb3356d688cd18f8b8d10da8bbbebb798dc8dff7195ca9731
3
+ size 985707981
pytorch_model-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a23b9f4de768578e892d42178b863df00303e6664a0bc233d404ad7b40b2ae
3
+ size 1059107643
pytorch_model-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9979aa74ea3af379f7503f267a47cf0cc2044e1c67b2fea266c83771249a434e
3
+ size 985686843
pytorch_model-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:977872dc18d84a92a9d3002fabc8f35b68aa30e78c3a598e45e8a2537e2f2699
3
+ size 1022407812
pytorch_model-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5697e0e795c0a949a8d3172517204c73d788808ede9064908f29d6a264f0c1d8
3
+ size 1022386674
pytorch_model-00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee11b8a08b98c13db0e3f1777f8decbbe479b54ffa5ee2d8a9426d907f416bb2
3
+ size 985707981
pytorch_model-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd752e8d3ef3349e5b04d11b803ffa400d06e35f6e062f1663c6f7e4f1bf5edb
3
+ size 1059107643
pytorch_model-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970b5642e0281b7ab222f8be4bd08b177ec48e4dfbd2a1cae044b07f0d746a43
3
+ size 985686843
pytorch_model-00012.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f742fc9d8afedc9e2afe51b8c87f4592821c9bc517b87c6b0de08568671899f8
3
+ size 1022407812
pytorch_model-00013.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:938263a28b9e8115823d53af3046abf9ec8a262842fa676eb2785b56372f1e01
3
+ size 1022386674
pytorch_model-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f7b3fae48d15301ff62b50f16ab1bb243e25a034d4142efb8d22c01b705d619
3
+ size 985707981
pytorch_model-00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a35e2d0b5fffeec2afc5a1e59a19ea455ed6c44751f430654f173e4fa9820a86
3
+ size 1059107643
pytorch_model-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e913e10aba8823b00dac575328c85b5cc35f155fb90d4ba3606a27df42da9df4
3
+ size 985686843
pytorch_model-00017.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a53251cee99fc9b4b68e59ccc70af836f195033c3f17ebcb59677b485ef4010
3
+ size 1022407812
pytorch_model-00018.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a125cb62850199387178a0a9fc85fd3ddc521d93742075475566934ad07fc4
3
+ size 1022386674
pytorch_model-00019.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d029aec9e4b3b0955b5b0852ce8f9c71a68a4fdffa8de94115a65282d8ca87
3
+ size 985707981
pytorch_model-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05248bb959caa6be7d282b5992d19e448596230edb15249fc0b4e4c381ece12a
3
+ size 1059107643
pytorch_model-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96f3100c2dec80afcd1311e74802fed3a3d3f9000ece6a18be25d0b31b9d1a11
3
+ size 985686843
pytorch_model-00022.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81a637a354100cc6abe3396f703d244cc754a9e698c232fc87f04c8580b0295e
3
+ size 1022407812
pytorch_model-00023.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d28f1560b6574b9df68dc6672cbac4144766cf975668cde0ed7f9a3bd0da65
3
+ size 1022386674
pytorch_model-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5553d0e724ff5cd7431c05117375e49bea0983fef3533b6f60a6e31cd2b24a4c
3
+ size 985707981
pytorch_model-00025.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7ffc89278ba8404b9aaf36bd37d64f2d61f815cc33671eb3ce6d9d9a2f35a2f
3
+ size 1059107643
pytorch_model-00026.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa8f95a9dec28400768caaac729837e722d73689e432935c035dd1f44964e4c
3
+ size 634422871
pytorch_model-00027.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36e56ccb5f75fbcb01773f2bfda8f299a6832ed636ed39b10aa65713025bf74
3
+ size 707625807
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 25550.478515625
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "pytorch_model-00001.bin",
7
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001.bin",
8
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001.bin",
9
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001.bin",
10
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001.bin",
11
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001.bin",
12
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002.bin",
13
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002.bin",
14
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002.bin",
15
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002.bin",
16
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002.bin",
17
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002.bin",
18
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002.bin",
19
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002.bin",
22
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002.bin",
23
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00002.bin",
24
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002.bin",
25
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002.bin",
26
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002.bin",
27
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003.bin",
28
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003.bin",
29
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003.bin",
30
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003.bin",
31
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003.bin",
32
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00003.bin",
33
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003.bin",
34
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003.bin",
35
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003.bin",
36
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003.bin",
37
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003.bin",
38
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003.bin",
39
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003.bin",
40
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00004.bin",
41
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00004.bin",
42
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004.bin",
43
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004.bin",
44
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004.bin",
45
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004.bin",
46
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004.bin",
47
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004.bin",
48
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00004.bin",
49
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00004.bin",
50
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00004.bin",
51
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004.bin",
52
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004.bin",
53
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004.bin",
54
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004.bin",
55
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004.bin",
56
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005.bin",
57
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00005.bin",
58
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00005.bin",
59
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00005.bin",
60
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005.bin",
61
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005.bin",
62
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005.bin",
63
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005.bin",
64
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005.bin",
65
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00005.bin",
66
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00005.bin",
67
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00005.bin",
68
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00005.bin",
69
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00005.bin",
70
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00006.bin",
71
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00006.bin",
72
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00006.bin",
73
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006.bin",
74
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006.bin",
75
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00006.bin",
76
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00006.bin",
77
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00006.bin",
78
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00006.bin",
79
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00006.bin",
80
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00006.bin",
81
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00006.bin",
82
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00006.bin",
83
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00006.bin",
84
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00007.bin",
85
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00007.bin",
86
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00007.bin",
87
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007.bin",
88
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00007.bin",
89
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00007.bin",
90
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00007.bin",
91
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00007.bin",
92
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00007.bin",
93
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00007.bin",
94
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00007.bin",
95
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00007.bin",
96
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00007.bin",
97
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00007.bin",
98
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00007.bin",
99
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00008.bin",
100
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008.bin",
101
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008.bin",
102
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00008.bin",
103
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00008.bin",
104
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00008.bin",
105
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00008.bin",
106
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00008.bin",
107
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00008.bin",
108
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00008.bin",
109
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00008.bin",
110
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00008.bin",
111
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00008.bin",
112
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00009.bin",
113
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00009.bin",
114
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009.bin",
115
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00009.bin",
116
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00009.bin",
117
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00009.bin",
118
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00009.bin",
119
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00009.bin",
120
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00009.bin",
121
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00009.bin",
122
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00009.bin",
123
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00009.bin",
124
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00009.bin",
125
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00009.bin",
126
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00009.bin",
127
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00009.bin",
128
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00010.bin",
129
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00010.bin",
130
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00010.bin",
131
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00010.bin",
132
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00010.bin",
133
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00010.bin",
134
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00010.bin",
135
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00010.bin",
136
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00010.bin",
137
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00010.bin",
138
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00010.bin",
139
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00010.bin",
140
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00010.bin",
141
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00010.bin",
142
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00011.bin",
143
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00011.bin",
144
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00011.bin",
145
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00011.bin",
146
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00011.bin",
147
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00011.bin",
148
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00011.bin",
149
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00011.bin",
150
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00011.bin",
151
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00011.bin",
152
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00011.bin",
153
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00011.bin",
154
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00011.bin",
155
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00011.bin",
156
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00012.bin",
157
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00012.bin",
158
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00012.bin",
159
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00012.bin",
160
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00012.bin",
161
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00012.bin",
162
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00012.bin",
163
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00012.bin",
164
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00012.bin",
165
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00012.bin",
166
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00012.bin",
167
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00012.bin",
168
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00012.bin",
169
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00012.bin",
170
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00012.bin",
171
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00013.bin",
172
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00013.bin",
173
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00013.bin",
174
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00013.bin",
175
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00013.bin",
176
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00013.bin",
177
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00013.bin",
178
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00013.bin",
179
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00013.bin",
180
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00013.bin",
181
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00013.bin",
182
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00013.bin",
183
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00013.bin",
184
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00014.bin",
185
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00014.bin",
186
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00014.bin",
187
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00014.bin",
188
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00014.bin",
189
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00014.bin",
190
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00014.bin",
191
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00014.bin",
192
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00014.bin",
193
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00014.bin",
194
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00014.bin",
195
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00014.bin",
196
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00014.bin",
197
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00014.bin",
198
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00014.bin",
199
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00014.bin",
200
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00015.bin",
201
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00015.bin",
202
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00015.bin",
203
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00015.bin",
204
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00015.bin",
205
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00015.bin",
206
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00015.bin",
207
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00015.bin",
208
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00015.bin",
209
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00015.bin",
210
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00015.bin",
211
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00015.bin",
212
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00015.bin",
213
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00015.bin",
214
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00016.bin",
215
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00016.bin",
216
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00016.bin",
217
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00016.bin",
218
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00016.bin",
219
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00016.bin",
220
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00016.bin",
221
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00016.bin",
222
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00016.bin",
223
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00016.bin",
224
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00016.bin",
225
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00016.bin",
226
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00016.bin",
227
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00016.bin",
228
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00017.bin",
229
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00017.bin",
230
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00017.bin",
231
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00017.bin",
232
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00017.bin",
233
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00017.bin",
234
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00017.bin",
235
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00017.bin",
236
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00017.bin",
237
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00017.bin",
238
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00017.bin",
239
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00017.bin",
240
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00017.bin",
241
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00017.bin",
242
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00017.bin",
243
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00018.bin",
244
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00018.bin",
245
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00018.bin",
246
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00018.bin",
247
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00018.bin",
248
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00018.bin",
249
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00018.bin",
250
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00018.bin",
251
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00018.bin",
252
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00018.bin",
253
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00018.bin",
254
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00018.bin",
255
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00018.bin",
256
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00019.bin",
257
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00019.bin",
258
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00019.bin",
259
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00019.bin",
260
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00019.bin",
261
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00019.bin",
262
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00019.bin",
263
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00019.bin",
264
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00019.bin",
265
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00019.bin",
266
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00019.bin",
267
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00019.bin",
268
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00019.bin",
269
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00019.bin",
270
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00019.bin",
271
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00019.bin",
272
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00020.bin",
273
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00020.bin",
274
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00020.bin",
275
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00020.bin",
276
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00020.bin",
277
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00020.bin",
278
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00020.bin",
279
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00020.bin",
280
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00020.bin",
281
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00020.bin",
282
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00020.bin",
283
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00020.bin",
284
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00020.bin",
285
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00020.bin",
286
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00021.bin",
287
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00021.bin",
288
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00021.bin",
289
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00021.bin",
290
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00021.bin",
291
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00021.bin",
292
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00021.bin",
293
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00021.bin",
294
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00021.bin",
295
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00021.bin",
296
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00021.bin",
297
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00021.bin",
298
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00021.bin",
299
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00021.bin",
300
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00022.bin",
301
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00022.bin",
302
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00022.bin",
303
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00022.bin",
304
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00022.bin",
305
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00022.bin",
306
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00022.bin",
307
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00022.bin",
308
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00022.bin",
309
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00022.bin",
310
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00022.bin",
311
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00022.bin",
312
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00022.bin",
313
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00022.bin",
314
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00022.bin",
315
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00023.bin",
316
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00023.bin",
317
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00023.bin",
318
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00023.bin",
319
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00023.bin",
320
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00023.bin",
321
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00023.bin",
322
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00023.bin",
323
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00023.bin",
324
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00023.bin",
325
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00023.bin",
326
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00023.bin",
327
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00023.bin",
328
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00024.bin",
329
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00024.bin",
330
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00024.bin",
331
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00024.bin",
332
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00024.bin",
333
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00024.bin",
334
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00024.bin",
335
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00024.bin",
336
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00024.bin",
337
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00024.bin",
338
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00024.bin",
339
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00024.bin",
340
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00024.bin",
341
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00024.bin",
342
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00024.bin",
343
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00024.bin",
344
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00025.bin",
345
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00025.bin",
346
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00025.bin",
347
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00025.bin",
348
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00025.bin",
349
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00025.bin",
350
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00025.bin",
351
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00025.bin",
352
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00025.bin",
353
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00025.bin",
354
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00025.bin",
355
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00025.bin",
356
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00025.bin",
357
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00025.bin",
358
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00026.bin",
359
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00026.bin",
360
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00026.bin",
361
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00026.bin",
362
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00026.bin",
363
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00026.bin",
364
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00026.bin",
365
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00026.bin",
366
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00026.bin",
367
+ "model.norm.weight": "pytorch_model-00026.bin",
368
+ "lm_head.weight": "pytorch_model-00027.bin"
369
+ }
370
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c07c5bc61607184c712c684d9d7b97c6dbfd5b7e428dfa79b95a35d0493e59
3
+ size 1052035
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }